Image de couverture de livre

Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zeng, Yirong, Ding, Xiao, Hou, Yutai, Wang, Yuxian, Du, Li, Dai, Juyi, Ding, Qiuyang, Tang, Duyu, Tu, Dandan, Liu, Weiwen, Qin, Bing, Liu, Ting
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use
par: Zeng, Yirong, et autres
Publié: (2025)

AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints
par: Zeng, Yirong, et autres
Publié: (2026)

The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?
par: Zeng, Yirong, et autres
Publié: (2026)

Precision over Diversity: High-Precision Reward Generalizes to Robust Instruction Following
par: Zeng, Yirong, et autres
Publié: (2026)

ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution
par: Huang, Xu, et autres
Publié: (2025)

ToolACE: Winning the Points of LLM Function Calling
par: Liu, Weiwen, et autres
Publié: (2024)

Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios
par: Huang, Shijue, et autres
Publié: (2024)

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
par: Guo, Jiahe, et autres
Publié: (2026)

Advancing and Benchmarking Personalized Tool Invocation for LLMs
par: Huang, Xu, et autres
Publié: (2025)

DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning
par: He, Yang, et autres
Publié: (2026)

ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning
par: Zeng, Xingshan, et autres
Publié: (2025)

The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
par: Xu, Haoyuan, et autres
Publié: (2026)

LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls
par: Zhang, Kangning, et autres
Publié: (2025)

Concise and Precise Context Compression for Tool-Using Language Models
par: Xu, Yang, et autres
Publié: (2024)

Tool Unlearning for Tool-Augmented LLMs
par: Cheng, Jiali, et autres
Publié: (2025)

ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
par: Ding, Peng, et autres
Publié: (2025)

ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
par: Tu, Dunwei, et autres
Publié: (2026)

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review
par: Jia, Xinda, et autres
Publié: (2025)

On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
par: Liu, Tong, et autres
Publié: (2026)

ToRL: Scaling Tool-Integrated RL
par: Li, Xuefeng, et autres
Publié: (2025)

Investigating Tool-Memory Conflicts in Tool-Augmented LLMs
par: Cheng, Jiali, et autres
Publié: (2026)

RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict
par: Zeng, Yirong, et autres
Publié: (2024)

ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis
par: Wang, Zezhong, et autres
Publié: (2024)

ToolFactory: Automating Tool Generation by Leveraging LLM to Understand REST API Documentations
par: Ni, Xinyi, et autres
Publié: (2025)

QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
par: Yu, Cong, et autres
Publié: (2025)

ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution
par: Huang, Junjie, et autres
Publié: (2026)

Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Calling
par: Ding, Peng, et autres
Publié: (2025)

ExpeTrans: LLMs Are Experiential Transfer Learners
par: Gao, Jinglong, et autres
Publié: (2025)

CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification
par: Chen, Jinpeng, et autres
Publié: (2026)

ToolRL: Reward is All Tool Learning Needs
par: Qian, Cheng, et autres
Publié: (2025)

AgenticRAG: Tool-Augmented Foundation Models for Zero-Shot Explainable Recommender Systems
par: Ma, Bo, et autres
Publié: (2025)

ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding
par: Liu, Xiao, et autres
Publié: (2026)

Teaching LLMs to Refine with Tools
par: Yu, Dian, et autres
Publié: (2024)

Ensuring Consistency for In-Image Translation
par: Fu, Chengpeng, et autres
Publié: (2024)

Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards
par: Jiayang, Cheng, et autres
Publié: (2026)

Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
par: Hao, Yupu, et autres
Publié: (2025)

Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
par: Feng, Zhangying, et autres
Publié: (2025)

A Survey on Data Quality Dimensions and Tools for Machine Learning
par: Zhou, Yuhan, et autres
Publié: (2024)

ReBrain: Brain MRI Reconstruction from Sparse CT Slice via Retrieval-Augmented Diffusion
par: Liu, Junming, et autres
Publié: (2025)

ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
par: Zeng, Xingshan, et autres
Publié: (2025)